Datasapiens is an international data-analytics startup based in Prague. We help our clients to uncover the value of their data and open up new revenue streams for them. We provide an end-to-end service that manages the data pipeline and automates the process of generating data insights.
In this talk, we will describe how we have solved an issue with large S3 API costs incurred by Presto under several usage concurrency levels by implementing Alluxio as a data orchestration layer between S3 and Presto. Also, we will show the results of an experiment with estimating the per-query S3 API costs using the TPC-DS dataset.
This talk will focus on:
- The Hadoop ecosystem at Datasapiens
- Drastic increase of S3 API costs during performance tests with Presto
- S3 API costs tests with TPC-DS
- Implications to the cloud data lake architecture
Datasapiens is an international data-analytics startup based in Prague. We help our clients to uncover the value of their data and open up new revenue streams for them. We provide an end-to-end service that manages the data pipeline and automates the process of generating data insights.
In this talk, we will describe how we have solved an issue with large S3 API costs incurred by Presto under several usage concurrency levels by implementing Alluxio as a data orchestration layer between S3 and Presto. Also, we will show the results of an experiment with estimating the per-query S3 API costs using the TPC-DS dataset.
This talk will focus on:
- The Hadoop ecosystem at Datasapiens
- Drastic increase of S3 API costs during performance tests with Presto
- S3 API costs tests with TPC-DS
- Implications to the cloud data lake architecture
Video:
Presentation Slides:
Videos:
Presentation Slides:
Complete the form below to access the full overview:
.png)
Videos
Fireworks AI is a leading inference cloud provider for Generative AI, powering real-time inference and fine-tuning services for customers' applications that require minimal latency, high throughput, and high concurrency. Their GPU infrastructure spans 10+ clouds and 15+ regions, serving enterprises and developers deploying production AI workloads at scale.
With model sizes reaching 70GB+, Fireworks AI faced critical challenges: eliminating cold start delays, managing highly concurrent model downloads across GPU clusters, reducing tens of thousands in annual cloud egress costs, and automating manual pipeline management that consumed 4+ hours weekly. They chose Alluxio as their solution to scale with their hyper-growth without requiring dedicated infrastructure resources.
In this tech talk, Akram Bawayah, Software Engineer at Fireworks AI, and Bin Fan, VP of Technology at Alluxio, share how Fireworks AI uses Alluxio to power their multi-cloud inference infrastructure.
They discuss:
- How Fireworks AI uses Alluxio in its high-performance model distribution system to deliver fast, reliable inference across multiple clouds
- How implementing Alluxio distributed caching achieved 1TB/s+ model deployment throughput, reducing model loading from hours to minutes while significantly cutting cloud egress costs
- How to simplify infrastructure operations and seamlessly scale model distribution across multi-cloud GPU environments
